# Google’s EmbeddingGemma 2 Adds Multimodal Search

> Google’s open-weight model maps text, code, images, video and audio into one embedding space, with smaller versions for on-device use.

Oossa · 2026-10-19 · https://oossa.com/en/google-s-embeddinggemma-2-adds-multimodal-search

Google’s EmbeddingGemma 2 is an open-weight model for search and retrieval that supports text, code, images, video and audio. Google says it maps them into a shared 768-dimensional space, so developers can search across media types without maintaining separate embedding spaces. The model is available on Hugging Face under the Apache 2.0 license.

Developers can load only the encoders they need: the model ranges from 270 million parameters for text and code to 740 million for full multimodal support. Its vectors can also be shortened to save memory, but Google reports that at 128 dimensions, retrieval quality falls to about 75% for images, video and speech.

## The facts

- License: Apache 2.0; available on Hugging Face.
- At 128 dimensions, Google reports about 90% of text quality and 75% of image, video and speech retrieval quality.

## Why it matters

Developers building local search can use one model to retrieve across documents and media, but shrinking vectors to save storage may reduce results for non-text searches; the source does not provide independent test results.

## Sources & references

1. [EmbeddingGemma 2 Expands Beyond Text to Support Code, Images, Video, and Audio](https://www.infoq.com/news/2026/10/embeddinggemma-2-multimodal/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering) – InfoQ, 2026-10-19

Last updated: 2026-10-19